IntroductionThe current methodologies for enzyme annotation primarily rely on established databases and classifications such as KEGG Orthology (KO), Enzyme Commission (EC) numbers, and Gene Ontology (GO) annotations, each with its specific focus and methodology. For instance, the EC system categorizes enzymes based on the chemical reactions they catalyze, providing a hierarchical numerical classification. KO links gene products to their functional orthologs across different species, whereas GO offers a broader ontology for describing the roles of genes and proteins in any organism. Despite their widespread use, these systems have notable limitations. The EC classification, while widely used, sometimes groups vastly different enzymes under the same category or subdivides similar ones excessively, based on the substrates they interact with--leading to ambiguities in enzyme function characterization.

The recent advancements of Large Language Models (LLMs), with their abundant world knowledge and capabilities of tool-using and reasoning, fostered many LLM planning algorithms. However, LLMs have not shown to be able to accurately solve complex combinatorial optimization problems. In Xie et al. (2024), the authors proposed TravelPlanner, a U.S. domestic travel planning benchmark, and showed that LLMs themselves cannot make travel plans that satisfy user requirements with a best success rate of 0.6%. In this work, we propose a framework that enables LLMs to formally formulate and solve the travel planning problem as a satisfiability modulo theory (SMT) problem and use SMT solvers interactively and automatically solve the combinatorial search problem. The SMT solvers guarantee the satisfiable of input constraints and the LLMs can enable a language-based interaction with our framework. When the input constraints cannot be satisfiable, our LLM-based framework will interactively offer suggestions to users to modify their travel requirements via automatic reasoning using the SMT solvers. We evaluate our framework with TravelPlanner and achieve a success rate of 97%. We also create a separate dataset that contain international travel benchmarks and use both dataset to evaluate the effectiveness of our interactive planning framework when the initial user queries cannot be satisfied. Our framework could generate valid plans with an average success rate of 78.6% for our dataset and 85.0% for TravelPlanner according to diverse humans preferences.

Uber has its eyes set on going public in 2019. CEO Dara Khosrowshahi said the ride-hailing startup is'on track' for an initial public offering in the second half of next year, saying Uber has a'very strong balance sheet' that could position it to do so. Khosrowshahi also shed some new light into Uber's self-driving car program, which has been paused in the wake of a fatal crash involving one of the firm's autonomous vehicles. Uber has its eyes set on an IPO in the second half of 2019, with CEO Dara Khosrowshahi saying the firm's in a'good position' in terms of profitability and margins to go public'We're in a good position in terms of the company's profile, in terms of profitability and margins continue to get better,' Khosrowshahi told CNBC at Recode's Code Conference in California. Khosrowshahi said he envisions Uber becoming the'Amazon for transportation,' serving as a platform for multiple transportation modes, like buses and bikes.

Machine learning helps financial services firms track customer happiness. By analysing user activity, smart machines can spot a potential account closure before it occurs. They can also track spending patterns and customer behaviour to offer tailored financial advice. Another application of machine learning is market analysis. Smart machines can be trained to track trading volatility or manage wealth and assets on behalf of an investor.

The 2005 Autonomous Agents and Multiagent Systems Conference (AAMAS 2005) was held July 25-29, 2005, at the University of Utrecht, the Netherlands. This report reviews the activities of that conference, including the workshop and tutorial programs, the main conference and poster tracks, the industry paper track, the demonstration track and sponsor demonstration sessions, the invited talks, exhibition, doctoral mentoring program, as well the sponsorship and scholarships activities. The Autonomous Agents and Multiagent Systems (AAMAS) conference series is the main conference venue for research in this area. It was initiated in 2002 as a merger of three conferences: the International Conference on Autonomous Agents, the International Conference on Multiagent Systems, and the International Workshop on Agent Theories, Architectures, and Languages. It aims to provide a highprofile and high-quality forum for research in the theory and practice of autonomous agents and multiagent systems.

The competition consists of two main tracks: the ASP system track and the model and solve track. The traditional system track compares dedicated answer set solvers on ASP benchmarks, while the model and solve track invites any researcher and developer of declarative knowledge representation systems to participate in an open challenge for solving sophisticated AI problems with their tools of choice. This article provides an overview of the ASP Competition series, reviews its origins and history, giving insights on organizing and running such an elaborate event, and briefly discusses the lessons learned so far. The main goal of ASP is to provide a versatile declarative modeling framework with many attractive characteristics. These features allow turning -- with little to no effort -- problem statements of computationally hard problems into executable formal specifications, also called answer set programs.

The competition has four tracks. The Gameplay and Learning tracks resemble traditional reinforcement learning competitions, the Level-Generation track focuses on the generation of entertaining game levels, and the Turing Test track focuses on humanlike game-playing behavior. We also outline some lessons learned from the competition and its future. The article is written by the four organizers of the competition. Within the CI/AI in games community, a series of competitions has grown up where competitors submit controllers for modified or reconstructed versions of existing computer games.

IPC-2014 was held in three separate parts to assess the state of the art in three prominent areas of planning research: the deterministic (classical) part (IPCD), the learning part (IPCL), and the probabilistic part (IPPC). Each part evaluated planning systems in ways that pushed the edge of existing planner performance by introducing new challenges, novel tasks, or both. The competition surpassed again the number of competitors that participated in its predecessor, highlighting the competition's central role in shaping the landscape of ongoing developments in evaluating planning systems. Actions are usually expressed in terms of preconditions and effects. Preconditions indicate the requirements that must hold to apply the action, while effects are the consequence (including the cost) of applying the action to the state of the world.

We review the First International Competition on Computational Models of Argumentation (ICCMA'15). The competition evaluated submitted solvers' performance on four different computational tasks related to solving abstract argumentation frameworks. Each task evaluated solvers in ways that pushed the edge of existing performance by introducing new challenges. Despite being the first competition in this area, the high number of competitors entered, and differences in results, suggest that the competition will help shape the landscape of ongoing developments in argumentation theory solvers. While still a young field when compared to areas such as SAT solving and logic programming, the argumentation community is very active, with a conference series (COMMA, which began in 2006) and a variety of workshops and special issues of journals.

The Turing test, as originally conceived, focused on language and reasoning; problems of perception and action were conspicuously absent. To serve as a benchmark for motivating and monitoring progress in AI research, this article proposes an extension to that original proposal that incorporates all four of these aspects of intelligence. Some initial suggestions are made regarding how best to structure such a test and how to measure progress. The proposed test also provides an opportunity to bring these four important areas of AI research back into sync after each has regrettably diverged into a fairly independent area of research of its own. He observed, however, that such a goal was somewhat ill-defined: how was one to conclude whether or not a machine was thinking (like a human)?